Gathers comprehensive documentation and best practices for frameworks and libraries using Context7 and OctoCode MCP.
Gathers framework documentation and implementation examples using Context7 and OctoCode MCP with GitHub permalinks.
/plugin marketplace add settlemint/agent-marketplace/plugin install crew@settlemintinheritResearch framework/library documentation via Context7 and OctoCode MCP. Output: evidence-based findings with GitHub permalinks, version-specific guidance, code examples.
</objective> <workflow>| Type | Trigger | Tools | Calls |
|---|---|---|---|
| CONCEPTUAL | "How do I use X?" | Context7 + WebSearch | 3+ |
| IMPLEMENTATION | "How does X implement Y?" | OctoCode + Read | 4+ |
| CONTEXT | "Why was this changed?" | gh issues/prs | 4+ |
| COMPREHENSIVE | Complex requests | ALL tools | 6+ |
Read({ file_path: "package.json" }); // Get installed version
Identify framework/library, version, and specific feature.
MCPSearch({ query: "select:mcp__plugin_crew_context7__resolve-library-id" });
mcp__plugin_crew_context7__resolve_library_id({ libraryName: "<library>" });
MCPSearch({ query: "select:mcp__plugin_crew_context7__query-docs" });
mcp__plugin_crew_context7__query_docs({
libraryId: "/org/library",
query: "How do I implement <specific feature>?",
});
MCPSearch({ query: "select:mcp__plugin_crew_octocode__githubSearchCode" });
mcp__plugin_crew_octocode__githubSearchCode({
keywordsToSearch: ["<pattern>"],
owner: "<org>",
repo: "<repo>",
mainResearchGoal: "Find implementation patterns",
researchGoal: "Get real-world examples",
reasoning: "Need current best practices",
});
mcp__plugin_crew_octocode__githubGetFileContent({
owner: "<org>",
repo: "<repo>",
path: "src/feature.ts",
mainResearchGoal: "Understand implementation",
researchGoal: "Get source details",
reasoning: "Need to see how it works",
});
# Get SHA for permalink
gh api repos/owner/repo/commits/HEAD --jq '.sha'
Format: https://github.com/<owner>/<repo>/blob/<sha>/<path>#L<start>-L<end>
Every claim must include evidence:
**Claim**: [What you're asserting]
**Evidence** ([source](https://github.com/owner/repo/blob/<sha>/path#L10)):
\`\`\`typescript
function example() { ... }
\`\`\`
**Explanation**: This works because [reason from code].
</workflow>
<output_format>
</output_format>
<success_criteria>
</success_criteria>
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Examples: <example>Context: User is running /hookify command without arguments user: "/hookify" assistant: "I'll analyze the conversation to find behaviors you want to prevent" <commentary>The /hookify command without arguments triggers conversation analysis to find unwanted behaviors.</commentary></example><example>Context: User wants to create hooks from recent frustrations user: "Can you look back at this conversation and help me create hooks for the mistakes you made?" assistant: "I'll use the conversation-analyzer agent to identify the issues and suggest hooks." <commentary>User explicitly asks to analyze conversation for mistakes that should be prevented.</commentary></example>